© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115316
    Prev
    Next
    INDEX
    Explanations

    speech and communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     visually
    -0.11
     physically
    -0.10
     Stub
    -0.10
     stub
    -0.10
    ampo
    -0.09
     Vir
    -0.09
    itra
    -0.09
    Env
    -0.09
     miraculous
    -0.09
    rix
    -0.09
    POSITIVE LOGITS
     aloud
    0.11
     spoken
    0.10
    -language
    0.10
    819
    0.10
     louder
    0.10
     kak
    0.09
     flu
    0.09
    -speaking
    0.09
     vo
    0.09
     tir
    0.09
    Activations Density 0.007%

    No Known Activations